Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    locations and topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uppercase
    0.41
    もう
    0.41
    новить
    0.41
    ’
    0.41
     স্টেট
    0.40
     धूमधाम
    0.38
    looms
    0.38
     ইমর
    0.38
    держание
    0.38
     subgroups
    0.38
    POSITIVE LOGITS
     relacion
    0.49
     مدرس
    0.47
    året
    0.45
    秞
    0.45
     разви
    0.44
     entusi
    0.44
     текста
    0.43
    ajit
    0.43
     реги
    0.42
     materia
    0.42
    Act Density 0.003%

    No Known Activations